DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation
Recommender systems are widely used in various real-world applications, but they often
encounter the persistent challenge of the user cold-start problem. Cross-domain …
encounter the persistent challenge of the user cold-start problem. Cross-domain …
[HTML][HTML] Physics Guided Neural Networks with Knowledge Graph
Over the past few decades, machine learning (ML) has demonstrated significant
advancements in all areas of human existence. Machine learning and deep learning models …
advancements in all areas of human existence. Machine learning and deep learning models …
Automated message selection for robust Heterogeneous Graph Contrastive Learning
Abstract Heterogeneous Graph Contrastive Learning (HGCL) has attracted lots of attentions
because of eliminating the requirement of node labels. The encoders used in HGCL mainly …
because of eliminating the requirement of node labels. The encoders used in HGCL mainly …
Multi-modal Robustness Fake News Detection with Cross-Modal and Propagation Network Contrastive Learning
Social media has transformed the landscape of news dissemination, characterized by its
rapid, extensive, and diverse content, coupled with the challenge of verifying authenticity …
rapid, extensive, and diverse content, coupled with the challenge of verifying authenticity …
Anatomical structures detection using topological constraint knowledge in fetal ultrasound
The accurate recognition of anatomical structures in fetal ultrasound images is crucial for
prenatal diagnosis and determining ultrasound standard planes. However, this task can be …
prenatal diagnosis and determining ultrasound standard planes. However, this task can be …
Weakly-Supervised Cross-Contrastive Learning Network for Image Manipulation Detection and Localization
R Bai - Knowledge-Based Systems, 2025 - Elsevier
With the significant reduction in the cost of image manipulation due to advancements in
image editing tools, it is crucial to investigate methods for detecting image manipulation …
image editing tools, it is crucial to investigate methods for detecting image manipulation …
Towards Graph Prompt Learning: A Survey and Beyond
Large-scale" pre-train and prompt learning" paradigms have demonstrated remarkable
adaptability, enabling broad applications across diverse domains such as question …
adaptability, enabling broad applications across diverse domains such as question …
[HTML][HTML] Cross-modal recipe retrieval based on unified text encoder with fine-grained contrastive learning
Cross-modal recipe retrieval is vital for transforming visual food cues into actionable cooking
guidance, making culinary creativity more accessible. Existing methods separately encode …
guidance, making culinary creativity more accessible. Existing methods separately encode …
Cluster-guided Contrastive Class-imbalanced Graph Classification
This paper studies the problem of class-imbalanced graph classification, which aims at
effectively classifying the categories of graphs in scenarios with imbalanced class …
effectively classifying the categories of graphs in scenarios with imbalanced class …
[HTML][HTML] Few-Shot Graph Anomaly Detection via Dual-Level Knowledge Distillation
X Li, D Cheng, L Zhang, C Zhang, Z Feng - Entropy, 2025 - mdpi.com
Graph anomaly detection is crucial in many high-impact applications across diverse fields. In
anomaly detection tasks, collecting plenty of annotated data tends to be costly and …
anomaly detection tasks, collecting plenty of annotated data tends to be costly and …